@inproceedings{doi-etal-2024-word,
title = "Word Order in {E}nglish-{J}apanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation",
author = "Doi, Kosuke and
Ko, Yuka and
Makinae, Mana and
Sudoh, Katsuhito and
Nakamura, Satoshi",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwslt-1.30",
pages = "254--264",
abstract = "This paper analyzes the features of monotonic translations, which follow the word order of the source language, in simultaneous interpreting (SI). Word order differences are one of the biggest challenges in SI, especially for language pairs with significant structural differences like English and Japanese. We analyzed the characteristics of chunk-wise monotonic translation (CMT) sentences using the NAIST English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset and identified some grammatical structures that make monotonic translation difficult in English-Japanese SI. We further investigated the features of CMT sentences by evaluating the output from the existing speech translation (ST) and simultaneous speech translation (simulST) models on the NAIST English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset as well as on existing test sets. The results indicate the possibility that the existing SI-based test set underestimates the model performance. The results also suggest that using CMT sentences as references gives higher scores to simulST models than ST models, and that using an offline-based test set to evaluate the simulST models underestimates the model performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doi-etal-2024-word">
<titleInfo>
<title>Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kosuke</namePart>
<namePart type="family">Doi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuka</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mana</namePart>
<namePart type="family">Makinae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper analyzes the features of monotonic translations, which follow the word order of the source language, in simultaneous interpreting (SI). Word order differences are one of the biggest challenges in SI, especially for language pairs with significant structural differences like English and Japanese. We analyzed the characteristics of chunk-wise monotonic translation (CMT) sentences using the NAIST English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset and identified some grammatical structures that make monotonic translation difficult in English-Japanese SI. We further investigated the features of CMT sentences by evaluating the output from the existing speech translation (ST) and simultaneous speech translation (simulST) models on the NAIST English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset as well as on existing test sets. The results indicate the possibility that the existing SI-based test set underestimates the model performance. The results also suggest that using CMT sentences as references gives higher scores to simulST models than ST models, and that using an offline-based test set to evaluate the simulST models underestimates the model performance.</abstract>
<identifier type="citekey">doi-etal-2024-word</identifier>
<location>
<url>https://aclanthology.org/2024.iwslt-1.30</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>254</start>
<end>264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation
%A Doi, Kosuke
%A Ko, Yuka
%A Makinae, Mana
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (in-person and online)
%F doi-etal-2024-word
%X This paper analyzes the features of monotonic translations, which follow the word order of the source language, in simultaneous interpreting (SI). Word order differences are one of the biggest challenges in SI, especially for language pairs with significant structural differences like English and Japanese. We analyzed the characteristics of chunk-wise monotonic translation (CMT) sentences using the NAIST English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset and identified some grammatical structures that make monotonic translation difficult in English-Japanese SI. We further investigated the features of CMT sentences by evaluating the output from the existing speech translation (ST) and simultaneous speech translation (simulST) models on the NAIST English-to-Japanese Chunk-wise Monotonic Translation Evaluation Dataset as well as on existing test sets. The results indicate the possibility that the existing SI-based test set underestimates the model performance. The results also suggest that using CMT sentences as references gives higher scores to simulST models than ST models, and that using an offline-based test set to evaluate the simulST models underestimates the model performance.
%U https://aclanthology.org/2024.iwslt-1.30
%P 254-264
Markdown (Informal)
[Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation](https://aclanthology.org/2024.iwslt-1.30) (Doi et al., IWSLT 2024)
ACL